refactor(tui): drop the TUI-local auto-title; titles come from the session-title service

Master's log-backed session-title capability already titles sessions durably
(deterministic fallback in the spine, optional model providers). Remove the
TUI's own autoTitle generation — the latch, prompt, cap, and llm stream call —
and keep the terminal rename: the TUI folds the logged title on mount and sets
'<session title> — <configured title>' on every accepted session/title event.
The tui-agent example and the scripted PTY fixture mount
session-title-first-message-llm so titles stay model-made; the scripted
adapter's tool-less branch now answers that provider's auxiliary request.

See .agents/notes/implemented/simplification/2026-07-22-tui-titles-from-session-title-service.md

examples/tui-agent/composition.md

@@ -23,6 +23,8 @@ flowchart LR
   bundle_agent_core --> spine_sessions["ctx.sessions"]
   bundle_agent_core --> spine_tools["ctx.tools + tool-bash"]
   bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"]
+  plugin_tui_session_title_llm["session-title-llm<br/>@deepseek-ai/dsh-session-title-first-message-llm"]
+  cfg --> plugin_tui_session_title_llm
   plugin_tui_token_meter["token-meter<br/>@deepseek-ai/dsh-token-meter"]
   cfg --> plugin_tui_token_meter
   plugin_tui_tool_result_prune["tool-result-prune<br/>@deepseek-ai/dsh-compact-tool-result-prune"]
@@ -67,6 +69,7 @@ flowchart LR
 | `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
 | `bash` | `@deepseek-ai/dsh-bash-local` |
 | `tui-agent` | `@deepseek-ai/dsh-tui-demo` |
+| `session-title-llm` | `@deepseek-ai/dsh-session-title-first-message-llm` |
 | `token-meter` | `@deepseek-ai/dsh-token-meter` |
 | `tool-result-prune` | `@deepseek-ai/dsh-compact-tool-result-prune` |
 | `compact-basic` | `@deepseek-ai/dsh-compact-basic` |

examples/tui-agent/cordis.yml

@@ -45,8 +45,6 @@
     ui:
       showReasoning: true
       maxToolOutputLines: 6
-      # Rename the terminal after the first message with a short model-made title.
-      autoTitle: true
     # Keep the persona to identity and behavior; tool plugins own tool guidance.
     # The loop resolves {{model}} from this agent's configuration.
     persona: |
@@ -55,6 +53,19 @@
       Verify your work by running the code or tests. Keep answers brief and
       factual.
 
+# Model-made session titles on the first-message cadence: replaces the spine's
+# deterministic fallback title with a short model summary. The TUI renders the
+# logged `session/title` as the banner subtitle and the terminal window title.
+# Omitting provider/model inherits the main request's exact route.
+- id: session-title-llm
+  name: '@deepseek-ai/dsh-session-title-first-message-llm'
+  config:
+    targetWords: 5
+    targetCjkCharacters: 10
+    maxInputBytes: 4096
+    maxOutputTokens: 64
+    timeoutMs: 60000
+
 # Replay-aware request pressure with one service-wide context window.
 - id: token-meter
   name: '@deepseek-ai/dsh-token-meter'

examples/tui-agent/tests/fixtures/tui-scripted-llm.ts

@@ -38,8 +38,9 @@ class ScriptedTuiAdapter extends LlmAdapter {
   }
 
   override async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
-    // The TUI's auto-title request carries no tool schemas, unlike every agent
-    // turn; answer it with a fixed title so the PTY test can assert the OSC set.
+    // The session-title provider's auxiliary request carries no tool schemas,
+    // unlike every agent turn; answer it with a fixed title so the PTY test can
+    // assert the logged title reaches the terminal window title.
     if ((options.tools?.length ?? 0) === 0) {
       for (const chunk of textChunks(TITLE_TEXT)) yield chunk
       return

examples/tui-agent/tests/fixtures/tui-scripted.cordis.yml

@@ -30,4 +30,15 @@
     persona: 'Scripted model {{model}}.'
     ui:
       showReasoning: true
-      autoTitle: true
+
+# Model-made session titles, as in the shipped cordis.yml: the scripted adapter
+# answers the tool-less title request with a fixed string so the PTY test can
+# assert the logged title reaches the terminal window title.
+- id: session-title-llm
+  name: '@deepseek-ai/dsh-session-title-first-message-llm'
+  config:
+    targetWords: 5
+    targetCjkCharacters: 10
+    maxInputBytes: 4096
+    maxOutputTokens: 64
+    timeoutMs: 10000

examples/tui-agent/tests/tui-keyless-smoke.e2e.ts

@@ -256,9 +256,11 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
     expect(output).toContain('How should the scripted run proceed?')
     expect(output).toContain('Safe')
     expect(output).toContain('Decision received. Scripted TUI run complete.')
-    // Auto-title: the first user message drives a tool-less title call that the
-    // scripted adapter answers, and the TUI sets it via OSC 0.
-    expect(output).toContain('\u001B]0;scripted session title\u0007')
+    // Session title: the first user message drives the first-message-llm
+    // provider's tool-less title call; the scripted adapter answers it, the
+    // accepted title lands in the log, and the TUI renders the terminal window
+    // title as `<session title> — <configured title>` via OSC 0.
+    expect(output).toContain('\u001B]0;scripted session title — DeepSeek Harness\u0007')
     expect(output).toContain('\u001B[?2004l')
   }, LOADER_SMOKE_TEST_TIMEOUT_MS)
 

examples/tui-agent/tests/tui.snapshot.ts

@@ -268,9 +268,6 @@ async function runScenario(scenario: Scenario): Promise<ScenarioResult> {
       color: true,
       showReasoning: true,
       title: 'DSH TUI snapshot',
-      // Off so replay stays deterministic: an auto-title request is not among the
-      // recorded turns. Auto-title's PTY coverage lives in the keyless smoke.
-      autoTitle: false,
       welcome: `Recorded replay: ${scenario.name}`,
       maxToolOutputLines: 8,
     }, {